Rin Arakaki

Product Manager, Technical Lead, Voice Team, Algoage

Nov 2025 — Current, Tokyo, Japan

Real-time AI copilot for contact-centre operators — telephony, transcription, knowledge and topic detection as one system on the customer's own stack.

• Founded a real-time AI copilot for contact centres and led product and engineering from inception, through on-site operator discovery, to deployments across seven customers, building the organisation from two to fourteen.
• Designed the copilot as an ambient agent embedded in customers' existing CRM and telephony workflows, absorbing platform differences through adapters and making extraction schemas, prompts and model selection configurable rather than customer-specific code.
• Established end-to-end evaluation for production voice AI, exercising synthetic calls through the real telephony path, scoring eleven dimensions with LLM judges, and grounding evaluation in operator accept-or-edit behaviour from live use.
• Established spec-driven, agent-operated development with executable engineering skills and agentic review, delivering 749 of 1,046 merged pull requests through coding agents without manually editing code.

Technologies — Amazon Connect, Twilio, LiveKit, WebRTC, Deepgram, Cartesia, Anthropic Claude, OpenAI, Gemini, Chrome Extension, Model Context Protocol, Spec Kit, Temporal, OpenTelemetry, pgvector, Amazon Web Services, Terraform

Software Engineer, Part-Time, Archemis

Oct 2025 — Current, Tokyo, Japan

AI-native crypto trading hedge fund.

• Translated quantitative research into a production Bitcoin-futures strategy, owning the specification, market-data integration, trading logic and deployment end to end in Rust.
• Introduced spec-driven development for quantitative strategies, auditing analyst definitions for contradictions and formalising ambiguous thresholds and edge cases, from missing market data to legitimately negative interest rates, before implementation.

Technologies — Rust, Google Cloud Platform, Kubernetes, Terraform

Software Engineer, aisaac

Jul 2025 — Nov 2025, Tokyo, Japan

Dating app for over-40s in Japan.

• Architected and shipped web payments to reduce app-store fees, spanning cross-platform authentication, subscription lifecycle, purchase tracking and refunds; the business reported a 30% improvement in ROAS.
• Built a next-month subscription-revenue forecast from retention and renewal rates, active subscriptions and expected new subscribers, informing advertising-spend decisions.

Technologies — SQL, TypeScript, Google Cloud Platform, React Native, Google Analytics, Adjust

Forward Deployed Engineer, JAPAN AI

Apr 2025 — Jun 2025, Tokyo, Japan

Customer deployments of the AI call centre product.

• Worked weekly with a call-centre client to elicit data, constraints and objectives, then formulated and shipped a constraint-programming agent matching operators to customer segments to maximise expected conversions under shift constraints.

Technologies — OR-Tools, C++, Python, Google Cloud Platform

Full-Stack Engineer, Speech Team, JAPAN AI

Oct 2024 — Apr 2025, Tokyo, Japan

LLM and generative AI research and development.

• Took ownership of an experimental real-time voice AI platform, leading it through inbound and outbound call-centre PoCs with three customers and into an official product.
• Researched UDP-based SIP and RTP protocols and Kubernetes networking to understand the failure modes of stateful voice workloads, then migrated the prototype onto LiveKit Agents and redesigned the boundary between the agent runtime and control plane.

Technologies — LiveKit, Twilio, SIP, WebRTC, Whisper, Kubernetes, gRPC, Python, Google Cloud Platform, RunPod

Full-Stack Engineer, Kakeai

Sep 2023 — Sep 2024, Tokyo, Japan

One-on-one meeting platform with real-time AI transcription and summarisation.

• Rebuilt the core calendar platform around a unified event and recurrence model, cutting its implementation from ~22K to ~7K lines while expanding its capabilities from advanced scheduling to enterprise mentor-mentee pairing with a stable matching algorithm.
• Analysed six quarterly survey waves and 7,400 one-on-one records to test whether platform adoption improved employee engagement; found a +1.96-point association but no dose-response effect, and designed propensity-score-matching and difference-in-differences analyses to separate adoption from selection.

Technologies — Python, TypeScript, Amazon Web Services, Terraform, Ruby on Rails

Lead Data Engineer, Viagate

Apr 2023 — Aug 2023, Tokyo, Japan

Marketing research platform using eye tracking and facial expression recognition.

• Anticipated that the pre-existing relational architecture would not scale for high-volume eye-tracking data and prepared a columnar alternative in parallel with the iOS engineer; when production proved the prediction, led the switch, and the prepared architecture carried the workload reliably.
• Built the data platform behind an advertising research product, aligning eye-tracking and facial-expression signals with video and web content, and added audience segmentation so clients could target research participants and compare responses across segments.

Technologies — OpenCV, Apache Arrow/Parquet, Protocol Buffers, PostgreSQL, Python, Amazon Web Services

Technical Lead, Operations Lead, Delipicks

Jun 2019 — May 2020, Tokyo, Japan

B2B food delivery startup; joined 6 months after launch.

• Led both technology and daily operations, working alongside the CEO to design business processes, software and operating procedures concurrently; ran over ten user interviews and took part in UX workshops to design the operator experience from first-hand use of the service.
• Recognised that menu selection and delivery routing had to be solved jointly to scale the business; formulated a revenue-maximisation problem balancing restaurant capacity and weekly menu variety against a 30-minute delivery constraint, then introduced combinatorial optimisation to replace manual planning.
• Built and managed the engineering team around the business's evolving technical needs, recruiting two engineers and the mathematical-optimisation specialist needed to take the planning approach into production.
• Worked directly across both sides of the marketplace with the CEO — from acquiring corporate customers to opening restaurant partnerships and deploying into supplier operations — then used sales and operational data to negotiate commercial terms, helping achieve positive unit economics.

Technologies — OR-Tools, Firebase, Python, JavaScript, Google Cloud Platform

Software Engineer, Styler

Aug 2018 — Mar 2019, Tokyo, Japan

Fashion retail platform bridging online and in-store experience (OMO — online-merge-offline).

• Planned the architectural transition to rapidly launch a new owned-media product alongside the existing Rails monolith; led the transition and product delivery, including metadata-based product discovery that improved on-site search and SEO.
• Helped build a six-nationality engineering team as development moved in-house from offshore, bridging the English-speaking engineers with Japanese product and business teams and establishing direct collaboration and shared ownership of release quality.

Technologies — Kubernetes, Python, Google Cloud Platform, Ruby on Rails

Software Engineer, MarketEnterprise

Apr 2016 — Dec 2017, Tokyo, Japan

Resale and rental business with complex internal operations.

• As the only engineer among more than fifteen new graduates in the on-the-job training programme, spent three months embedded across sales and fulfilment operations — from call-centre purchasing, photography and listing to logistics — to understand the workflows first-hand and design the internal systems around them.
• Modernised the legacy platform by designing and implementing the organisation-wide fine-grained access control API, establishing the foundation for the company's transition to microservices; resolved a stalled performance issue by reducing authorisation latency from 7 seconds to 0.2 seconds.

Technologies — MySQL, Python, JavaScript, Amazon Web Services

The Open University of Japan, Bachelor's Degree, Liberal Arts

Apr 2012 — Mar 2016, Tokyo, Japan

• Completed degree requirements in 2 years.

Founder, Synthetic

Dec 2020 — Present, Tokyo, Japan

Independent research initiative — formal AI reasoning and automated proof generation. Self-funded and self-directed since 2020; sustained across 5,000+ commits.

• Designing a graph and network-based search and indexing system for mathematical formulae, applied to automated theorem discovery.
• Investigating the theorem provers — Lean, Coq, Isabelle — and their proof search engines.
• Researching formal proof generation through LLM and reinforcement-learning feedback loops.

Technologies — Rust, Python, TypeScript